Pre-fetching and Pre-releasing Based LRU for Efficient/Reliable Cache Management

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Many block replacement schemes have been proposed to enhance hit ratios by maintaining blocks that will frequently be re-referenced in buffer cache in the future. And the LRU block replacement scheme is still widely used due to its simplicity and good adaptability to the changes of the working set. However, LRU has a severe drawback that exhibits itself in performance degradation in access patterns with weak locality such as sequential and looping reference. In this paper, we propose an efficient LRU buffer cache management scheme using pre-fetching and pre-releasing based on spatial locality. It is as simple as the LRU scheme and retains characteristics of LRU. Trace-driven simulation experiments show that the hit ratios are improved up to about 24% (with an average of 18%) compared to the LRU scheme for the workloads we use.

Original languageEnglish
Title of host publication19th International Conference on Computers and Their Applications 2004, CATA 2004
EditorsBidyut Gupta
PublisherThe International Society for Computers and Their Applications (ISCA)
Pages220-223
Number of pages4
ISBN (Electronic)9781618395511
StatePublished - 2004
Event19th International Conference on Computers and Their Applications, CATA 2004 - Seattle, United States
Duration: 18 Mar 200420 Mar 2004

Publication series

Name19th International Conference on Computers and Their Applications 2004, CATA 2004

Conference

Conference19th International Conference on Computers and Their Applications, CATA 2004
Country/TerritoryUnited States
CitySeattle
Period18/03/0420/03/04

Fingerprint

Dive into the research topics of 'Pre-fetching and Pre-releasing Based LRU for Efficient/Reliable Cache Management'. Together they form a unique fingerprint.

Cite this